Delphi’s COVIDcast Project:
API and Client Access Tools

Katie Mazaitis* and Ryan Tibshirani†
*†Machine Learning and †Statistics
Carnegie Mellon University
†Amazon Scholar, AWS Labs




September 1, 2020

Delphi Then

Delphi Now

COVIDcast

The COVIDcast project has many parts:

  1. Unique relationships with partners in tech and healthcare granting us access to data on pandemic activity
  2. Code and infrastructure to build COVID-19 indicators, continuously-updated and geographically-comprehensive
  3. A historical database of all indicators, including revision tracking, with over 500 million observations
  4. A public API serving new indicators daily (and R and Python packages for client support)
  5. Interactive maps and graphics to display our indicators
  6. Forecasting and modeling work building on the indicators

Severity Pyramid

What Is This Used For?

COVIDcast Indicators

COVIDcast Indicators (Cont.)

This Talk

Today: COVIDcast API and client access in R. Outline:

Note: examples are meant to be demos, all code included


Next talks: Facebook surveys, medical claims data, etc.

Example: Deaths

How many people have died from COVID-19 per day, in my state, since March 1?

library(covidcast)
deaths = covidcast_signal(data_source = "usa-facts", 
                          signal = "deaths_7dav_incidence_num", 
                          start_day = "2020-03-01", end_day = "2020-08-30",
                          geo_type = "state", geo_values = "pa")

plot(deaths, plot_type = "line", 
     title = "COVID-19 deaths in PA (7-day trailing average)")

Example: Hospitalizations

What percentage of daily hospital admissions are due to COVID-19 in PA, NY, TX?

hosp = covidcast_signal(data_source = "hospital-admissions", 
                        signal = "smoothed_adj_covid19",
                        start_day = "2020-03-01", end_day = "2020-08-28",
                        geo_type = "state", geo_values = c("pa", "ny", "tx"))

plot(hosp, plot_type = "line", 
     title = "% of hospital admissions due to COVID-19")

Example: Cases

What does the current COVID-19 incident case rate look like, nationwide?

cases = covidcast_signal(data_source = "usa-facts", 
                         signal = "confirmed_7dav_incidence_prop",
                         start_day = "2020-08-30", end_day = "2020-08-30")

plot(cases, title = "Daily new COVID-19 cases per 100,000 people")

Example: Cases (Cont.)

What does the current COVID-19 cumulative case rate look like, nationwide?

cases = covidcast_signal(data_source = "usa-facts", 
                         signal = "confirmed_cumulative_prop",
                         start_day = "2020-08-30", end_day = "2020-08-30")

plot(cases, title = "Cumulative COVID-19 cases per 100,000 people", 
     choro_params = list(legend_n = 6))

Example: Cases (Cont.)

Where is the current COVID-19 cumulative case rate greater than 2%?

plot(cases, choro_col = c("#D3D3D3", "#FFC0CB"), 
     title = "Cumulative COVID-19 cases per 100,000 people",
     choro_params = list(breaks = c(0, 2000), legend_width = 5))

Example: Doctor’s Visits

How do some major cities compare in terms of doctor’s visits due to COVID-like illness?

dv = covidcast_signal(data_source = "doctor-visits", 
                      signal = "smoothed_adj_cli", 
                      start_day = "2020-03-01", end_day = "2020-08-28",
                      geo_type = "msa", 
                      geo_values = name_to_cbsa(c("Pittsburgh", "New York", 
                                                  "San Antonio", "Miami")))

plot(dv, plot_type = "line", 
     title = "% of doctor's visits due to COVID-like illness")

Example: Symptoms

How do my county and my friend’s county compare in terms of people reporting that they know somebody with COVID symptoms?

sympt = covidcast_signal(data_source = "fb-survey", 
                         signal = "smoothed_hh_cmnty_cli",
                         start_day = "2020-04-15", end_day = "2020-08-30",
                         geo_values = c(name_to_fips("Allegheny"),
                                        name_to_fips("Fulton", state = "GA")))

plot(sympt, plot_type = "line", range = range(sympt$value),
     title = "% of people who know somebody with COVID symptoms")

API Specification

The COVIDcast API is based on HTTP GET queries and returns data in JSON form. The base URL is https://api.covidcast.cmu.edu/epidata/api.php?source=covidcast


Parameter Description Examples
data_source data source doctor-visits or fb-survey
signal signal derived from data source smoothed_cli or smoothed_adj_cli
time_type temporal resolution of the signal day or week
geo_type spatial resolution of the signal county, hrr, msa, or state
time_values time units over which events happened 20200406 or 20200406-20200410
geo_value location codes, depending on geo_type * for all, or pa for Pennsylvania

Example: API Query

Estimated % COVID-like illness on April 6, 2020 from the Facebook survey, in Allegheny County: https://api.covidcast.cmu.edu/epidata/api.php?source=covidcast&data_source=fb-survey&signal=raw_cli&time_type=day&geo_type=county&time_values=20200406&geo_value=42003

library(jsonlite)
res = readLines("https://api.covidcast.cmu.edu/epidata/api.php?source=covidcast&data_source=fb-survey&signal=raw_cli&time_type=day&geo_type=county&time_values=20200406&geo_value=42003")
prettify(res)
## {
##     "result": 1,
##     "epidata": [
##         {
##             "geo_value": "42003",
##             "signal": "raw_cli",
##             "time_value": 20200406,
##             "direction": null,
##             "issue": 20200903,
##             "lag": 150,
##             "value": 0.7614984,
##             "stderr": 0.3826746,
##             "sample_size": 434.8891
##         }
##     ],
##     "message": "success"
## }
##

API Documentation

For full details, see the API documentation site. There you’ll also find details on:

As Of, Issues, Lag

By default the API returns the most recent data for each time_value. We also provide access to all previous versions of the data, using the following optional parameters:


Parameter To get data … Examples
as_of as if we queried the API on a particular date 20200406
issues published at a particular date or date range 20200406 or 20200406-20200410
lag published a certain number of time units after events occured 1 or 3

Data Revisions

Why would we need this? Because many data sources are subject to revisions:

This presents a challenge to modelers: e.g., we have to learn how to forecast based on the data we’d have at the time, not updates that would arrive later

To accommodate, we log revisions even when the original data source does not!

covidcast R Package

We also provide an R package called covidcast for API access. Highlights:

covidcast R Package (Cont.)

Still highly under development … much more to come. For now, check out our vignettes:

(Or, you can file an issue or contribute a pull request on our public GitHub repo!)

Example: Backfill in Doctor’s Visits Signal

Let’s examine the revisions or “backfill” present in our doctor’s visits signal. We’ll look at this signal over the month of June, and query the API “as of” each week from June 8 through August 1:

# Loop over "as of" dates, fetch data from the API for each one
as_ofs = seq(as.Date("2020-06-08"), as.Date("2020-08-01"), by = "week")
states = c("az", "ca", "pa", "ny")
dv_as_of = map_dfr(as_ofs, function(as_of) {
  covidcast_signal(data_source = "doctor-visits", signal = "smoothed_adj_cli",
                   start_day = "2020-06-01", end_day = "2020-06-30", 
                   geo_type = "state", geo_values = states, as_of = as_of)
})
dv_as_of$geo_value = factor(dv_as_of$geo_value, levels = states, 
                            labels = abbr_to_name(states, ignore.case = TRUE))

# Now plot the each "as of" time series curve, faceted by state
ggplot(dv_as_of, aes(x = time_value, y = value)) + 
  geom_line(aes(color = factor(issue))) + facet_wrap(vars(geo_value)) + 
  labs(color = "Issue date", x = "Date", y = "% doctor's visits due to CLI") +
  theme_bw() + theme(legend.pos = "bottom")

Example: Correlations Between Cases and Deaths

Now let’s examine the correlations between COVID-19 cases and deaths, per day, across counties. We’ll look at Spearman correlation, starting March 1. Then repeat but for cases lagged back 7 days:

# Fetch confirmed cases and deaths, at the county level, since March 1
start_day = "2020-03-01"
end_day = "2020-08-30"
cases = covidcast_signal("usa-facts", "confirmed_7dav_incidence_num", 
                         start_day, end_day)
deaths = covidcast_signal("usa-facts", "deaths_7dav_incidence_num", 
                          start_day, end_day)

# Consider only "active" counties with at least 500 cumulative cases so far
case_num = 500
geo_values = covidcast_signal("usa-facts", "confirmed_cumulative_num",
                              max(cases$time), max(cases$time)) %>%
  filter(value >= case_num) %>% pull(geo_value)
cases_act = cases %>% filter(geo_value %in% geo_values)
deaths_act = deaths %>% filter(geo_value %in% geo_values)

# Compute correlations, per time, over all counties. Both with original time
# alignment, and with cases lagged backwards in time by 7 days
df_cor1 = covidcast_cor(cases_act, deaths_act, by = "time_value", 
                        method = "spearman")
df_cor2 = covidcast_cor(cases_act, deaths_act, by = "time_value", 
                        method = "spearman", dt_x = -7)

# Stack rowwise into one data frame, then plot time series
df_cor = rbind(df_cor1, df_cor2)
df_cor$dt = factor(c(rep(0, nrow(df_cor1)), rep(-7, nrow(df_cor2))))
ggplot(df_cor, aes(x = time_value, y = value)) +
  geom_line(aes(color = dt)) +
  labs(title = "Correlation between cases and deaths",
       subtitle = sprintf("Over counties with at least %i cases", case_num),
       x = "Date", y = "Correlation") + 
  theme_bw() + theme(legend.position = "bottom")

Thanks

Go to: https://covidcast.cmu.edu … you’ll find everything linked from there!


Delphi Carnegie Mellon University

Appendix: Current Metadata

meta = covidcast_meta()
summary(meta)
## A `covidcast_meta` data frame with 322 rows and 15 columns.
## 
## Number of data sources : 11
## Number of signals      : 88
## 
## Summary:
## 
##  data_source           signal                         county msa hrr state
##  doctor-visits         smoothed_adj_cli               *      *   *   *    
##  doctor-visits         smoothed_cli                   *      *   *   *    
##  fb-survey             raw_cli                        *      *   *   *    
##  fb-survey             raw_hh_cmnty_cli               *      *   *   *    
##  fb-survey             raw_ili                        *      *   *   *    
##  fb-survey             raw_nohh_cmnty_cli             *      *   *   *    
##  fb-survey             raw_wcli                       *      *   *   *    
##  fb-survey             raw_whh_cmnty_cli              *      *   *   *    
##  fb-survey             raw_wili                       *      *   *   *    
##  fb-survey             raw_wnohh_cmnty_cli            *      *   *   *    
##  fb-survey             smoothed_cli                   *      *   *   *    
##  fb-survey             smoothed_hh_cmnty_cli          *      *   *   *    
##  fb-survey             smoothed_ili                   *      *   *   *    
##  fb-survey             smoothed_nohh_cmnty_cli        *      *   *   *    
##  fb-survey             smoothed_wcli                  *      *   *   *    
##  fb-survey             smoothed_whh_cmnty_cli         *      *   *   *    
##  fb-survey             smoothed_wili                  *      *   *   *    
##  fb-survey             smoothed_wnohh_cmnty_cli       *      *   *   *    
##  ght                   raw_search                            *   *   *    
##  ght                   smoothed_search                       *   *   *    
##  google-survey         raw_cli                        *      *   *   *    
##  google-survey         smoothed_cli                   *      *   *   *    
##  hospital-admissions   smoothed_adj_covid19           *      *   *   *    
##  hospital-admissions   smoothed_covid19               *      *   *   *    
##  indicator-combination confirmed_7dav_cumulative_num  *      *   *   *    
##  indicator-combination confirmed_7dav_cumulative_prop *      *   *   *    
##  indicator-combination confirmed_7dav_incidence_num   *      *   *   *    
##  indicator-combination confirmed_7dav_incidence_prop  *      *   *   *    
##  indicator-combination confirmed_cumulative_num       *      *   *   *    
##  indicator-combination confirmed_cumulative_prop      *      *   *   *    
##  indicator-combination confirmed_incidence_num        *      *   *   *    
##  indicator-combination confirmed_incidence_prop       *      *   *   *    
##  indicator-combination deaths_7dav_cumulative_num     *      *   *   *    
##  indicator-combination deaths_7dav_cumulative_prop    *      *   *   *    
##  indicator-combination deaths_7dav_incidence_num      *      *   *   *    
##  indicator-combination deaths_7dav_incidence_prop     *      *   *   *    
##  indicator-combination deaths_cumulative_num          *      *   *   *    
##  indicator-combination deaths_cumulative_prop         *      *   *   *    
##  indicator-combination deaths_incidence_num           *      *   *   *    
##  indicator-combination deaths_incidence_prop          *      *   *   *    
##  indicator-combination nmf_day_doc_fbc_fbs_ght        *      *       *    
##  indicator-combination nmf_day_doc_fbs_ght            *      *       *    
##  jhu-csse              confirmed_7dav_cumulative_num  *      *   *   *    
##  jhu-csse              confirmed_7dav_cumulative_prop *      *   *   *    
##  jhu-csse              confirmed_7dav_incidence_num   *      *   *   *    
##  jhu-csse              confirmed_7dav_incidence_prop  *      *   *   *    
##  jhu-csse              confirmed_cumulative_num       *      *   *   *    
##  jhu-csse              confirmed_cumulative_prop      *      *   *   *    
##  jhu-csse              confirmed_incidence_num        *      *   *   *    
##  jhu-csse              confirmed_incidence_prop       *      *   *   *    
##  jhu-csse              deaths_7dav_cumulative_num     *      *   *   *    
##  jhu-csse              deaths_7dav_cumulative_prop    *      *   *   *    
##  jhu-csse              deaths_7dav_incidence_num      *      *   *   *    
##  jhu-csse              deaths_7dav_incidence_prop     *      *   *   *    
##  jhu-csse              deaths_cumulative_num          *      *   *   *    
##  jhu-csse              deaths_cumulative_prop         *      *   *   *    
##  jhu-csse              deaths_incidence_num           *      *   *   *    
##  jhu-csse              deaths_incidence_prop          *      *   *   *    
##  quidel                covid_ag_raw_pct_positive      *      *   *   *    
##  quidel                covid_ag_smoothed_pct_positive *      *   *   *    
##  quidel                raw_pct_negative                      *       *    
##  quidel                raw_tests_per_device                  *       *    
##  quidel                smoothed_pct_negative                 *       *    
##  quidel                smoothed_tests_per_device             *       *    
##  safegraph             completely_home_prop           *              *    
##  safegraph             full_time_work_prop            *              *    
##  safegraph             median_home_dwell_time         *              *    
##  safegraph             part_time_work_prop            *              *    
##  usa-facts             confirmed_7dav_cumulative_num  *      *   *   *    
##  usa-facts             confirmed_7dav_cumulative_prop *      *   *   *    
##  usa-facts             confirmed_7dav_incidence_num   *      *   *   *    
##  usa-facts             confirmed_7dav_incidence_prop  *      *   *   *    
##  usa-facts             confirmed_cumulative_num       *      *   *   *    
##  usa-facts             confirmed_cumulative_prop      *      *   *   *    
##  usa-facts             confirmed_incidence_num        *      *   *   *    
##  usa-facts             confirmed_incidence_prop       *      *   *   *    
##  usa-facts             deaths_7dav_cumulative_num     *      *   *   *    
##  usa-facts             deaths_7dav_cumulative_prop    *      *   *   *    
##  usa-facts             deaths_7dav_incidence_num      *      *   *   *    
##  usa-facts             deaths_7dav_incidence_prop     *      *   *   *    
##  usa-facts             deaths_cumulative_num          *      *   *   *    
##  usa-facts             deaths_cumulative_prop         *      *   *   *    
##  usa-facts             deaths_incidence_num           *      *   *   *    
##  usa-facts             deaths_incidence_prop          *      *   *   *    
##  youtube-survey        raw_cli                                       *    
##  youtube-survey        raw_ili                                       *    
##  youtube-survey        smoothed_cli                                  *    
##  youtube-survey        smoothed_ili                                  *